© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 15323
    Prev
    Next
    INDEX
    Explanations

    information about traveling and security procedures, particularly related to carrying items like bottles through security checkpoints

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    480
    +0.18
    0.9%
    464
    +0.17
    0.9%
    71
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    685
    +0.18
    0.02
    393
    +0.17
    0.10
    678
    +0.16
    0.03
    Negative Logits
     mull
    -0.53
     Cadillac
    -0.48
     Hutchinson
    -0.47
     Murdoch
    -0.46
     Hogan
    -0.46
     marrow
    -0.45
     swat
    -0.45
     tire
    -0.45
     Fischer
    -0.44
     casino
    -0.44
    POSITIVE LOGITS
    etheless
    0.79
    SourceFile
    0.69
    heres
    0.65
    FORE
    0.61
    ardless
    0.58
     PLUS
    0.58
     uncond
    0.57
    again
    0.57
    esides
    0.57
    rarily
    0.56
    Activations Density 1.500%

    No Known Activations